The aim of this paper is to address the dilemma of supply chain management (SCM) within a truly Pareto-based multi-objective context. This is done by introducing an integration of system dynamics and multi-objective optimisation. An extended version of the well-known pedagogical SCMproblem, the Beer Game, originally developed at MIT since the 1960s, has been used as the illustrative example. As will be discussed in the paper, the integrated multi-objective optimisation and system dynamics model has been shown to be very useful for revealing how the parameters in the Beer Game affect the optimality of the three common SCM objectives, namely, the minimisation of inventory cost, backlog cost, and the bullwhip effect.
The aim of this paper is to address the dilemma of Supply Chain Management (SCM) within a truly Pareto-based multi-objective context. This is done by introducing an integration of System Dynamics and Multi-Objective Optimization. Specifically, the paper contrasts local optimization with global optimization for SCM in which optimal trade-off solutions in the entity level, i.e. optimizing the supply chain from the perspectives of individual (local) entities. e.g., supplier, factory, distributor and retailer, are collected and compared to those obtained from an overall supply chain level (global) optimization. An extended version of the well-known pedagogical SCM problem, the Beer Game, originally developed at MIT since the 1960s, has been used as the illustrative example. As will be discussed in the paper, the integrated multi-objective optimization and system dynamics model has been shown to be very useful for revealing that how the parameters in the Beer Game affect the optimality of the three common SCM objectives, namely, the minimization of inventory, backlog, and the bullwhip effect.
This study investigates the potential of Mixed Reality (MR) in the manual assembly processes and conducts a case study at a pump manufacturing plant in Sweden. An MR solution is developed to assist operators through visual instructions and guiding aides. The solution also captures the operator's motions using advanced hand and eye tracking features for real-time guidance and accurate time measurement. The proposed MR solution uses the build feature of HoLolens and a workstation editor, which facilitates the use of the solution in diverse assembly environments. The results of the experiments show that the developed MR solution can improve operator support, reduce errors, and enhance the overall efficiency of manual assembly processes. Moreover, it is shown to be an efficient tool for time measurement of the manual assembly process that has promising potential to replace sophisticated and time-consuming traditional time study methods.
The use of simulation to improve existing manufacturing systems is not new, but simulation can also be used increase the understanding of production systems that have not yet been built. The power of simulation models can be further enhanced by using simulation-based optimization, in which an optimization algorithm tries to find optimal solutions, given certain objectives. However, extracting knowledge from the data resulting from simulation experiments and simulation-based optimization is a complex task. Therefore, tools are needed to assist users in this task. These tools can be visual, like diagrams, or can be generated by data mining. The process of running a study using simulation-based optimization to extract knowledge is a manual task that can in part be automated using existing tools, but to the author’s knowledge there is no software that implements the complete process. This work aims to develop a novel decision support system to support the generic decision process when using simulation and simulation-based optimization. The first step in setting up such a system is to understand how industry currently uses simulation and simulation-based optimization in manufacturing operations. Thus a questionnaire was distributed to manufacturing companies and organizations. The results showed that these techniques are being used, but that companies want more help with the analysis of the results as well as an automated guide in the decision process. This work proposes a system that supports a generic decision process by providing a tool with which a user can define a workflow in their organization, using simulation-based optimization as one component. The decision support system then provides tools for extracting knowledge in the form of diagrams and performs data mining for automated analysis. Data mining is part of the workflow as a tool for extracting knowledge after an optimization, as well as a tool for guiding optimization to suit the users’ preferences. The decision support system also provides for visualization of simulation models and optimization results using augmented reality. A head-mounted display helps users to see the results and model behaviors in 3D. This technology also makes it possible for users to collaborate, both in the same location and remotely. These visual and automatic analysis tools are shown to be effective in several application studies of real-world production scenarios in which data mining has been used to extract important knowledge that would be hard to obtain manually. Together with the automated workflow and efficient visualization of simulation and optimization results in augmented reality, the decision support system is believed to be an effective tool for extracting knowledge for general production systems design and analysis.
The integration of simulation-based optimization and data mining is an emerging approach to support decision-making in the design and improvement of manufacturing systems. In such an approach, knowledge extracted from the optimal solutions generated by the simulation-based optimization process can provide important information to decision makers, such as the importance of the decision variables and their influence on the design objectives, which cannot easily be obtained by other means. However, can the extracted knowledge be directly used during the optimization process to further enhance the quality of the solutions? This paper proposes such an online knowledge extraction approach that is used together with a preference-guided multi-objective optimization algorithm on simulation models of manufacturing systems. Specifically, it introduces a combination of the multi-objective evolutionary optimization algorithm, NSGA-II, and a customized data mining algorithm, called Flexible Pattern Mining (FPM), which can extract knowledge in the form of rules in an online and automatic manner, in order to guide the optimization to converge towards a decision maker's preferred region in the objective space. Through a set of application problems, this paper demonstrates how the proposed FPM-NSGA-II can be used to support higher quality decision-making in manufacturing.
Although the idea of using Augmented Reality and simulation within manufacturing is not a new one, the improvement of hardware enhances the emergence of new areas. For manufacturing organizations, simulation is an important tool used to analyze and understand their manufacturing systems; however, simulation models can be complex. Nonetheless, using Augmented Reality to display the simulation results and analysis can increase the understanding of the model and the modeled system. This paper introduces a decision support system, IDSS-AR, which uses simulation and Augmented Reality to show a simulation model in 3D. The decision support system uses Microsoft HoloLens, which is a head-worn hardware for Augmented Reality. A prototype of IDSS-AR has been evaluated with a simulation model depicting a real manufacturing system on which a bottleneck detection method has been applied. The bottleneck information is shown on the simulation model, increasing the possibility of realizing interactions between the bottlenecks.
Designing or improving a manufacturing system involves a series of complex decisions over time to satisfy the strategic objectives of the company. To select the optimal parameters of the system entities so as to achieve the desired overall performance of the system is a very complex task that has been proven to be difficult, even for a seasoned decision maker. One of the major barriers for more efficient decision making in manufacturing is that whilst there is in principle abundant data from various levels of the factory, these data need to be organized and transferred into knowledge suitable for decision-making support. The integration of decision-making support and knowledge management has been identified to be more and more important in both scientific research and from industrial companies. The concept of deciphering knowledge from multi-objective optimization was first proposed by Deb with the term innovization (innovation via optimization). By integrating the concept of innovization with simulation, a new set of powerful tools for manufacturing systems analysis, in order to support optimal decision making in design and improvement activities, is emerged. This method is so-called Simulation-based Innovization (SBI), which has been proven to produce promising results in our previous application studies. Nevertheless, to promote the wider use of such a new method requires the development of an integrated software toolset. The goal of this paper is therefore to outline a Cloud-computing based system architecture for implementing such a SBI-based Interactive Decision Support System.
This paper describes a decision support system (DSS) built on knowledge extraction using simulation-based optimization and data mining. The paper starts with a requirements analysis based on a survey conducted with a number of industrial companies about their practices of using simulations for decision support.Based upon the analysis, a new, interactive DSS that can fulfill the industrial requirements, is proposed.The design of the cloud-based system architecture of the DSS is then described. To show the functionality and potential of the proposed DSS, an application study has been performed for the optimal design of a hypothetical but realistic flexible production cell. How important knowledge with respect to different preferences of the decision maker can be generated as rules, using the new Flexible Pattern Mining algorithm provided in the DSS, will be revealed by the results of this application study.
Simulation-based innovization is a method for extracting knowledge from a simulation model and optimization. This method can help decision makers to make high-quality decisions for their manufacturing systems so as to enhance the competitiveness of companies. Nevertheless, the simulation-based innovization process can be computationally costly and having these resources in-house can be expensive. By running the process in a cloud environment instead, the company only pays for the resources they are using. This paper proposes the concept of a cloud-based computing platform that can run the simulation-based innovization process and discuss its possibilities and challenges.
Industry is foreseeing rapid developments in the ability tocapture data within its manufacturing operations and the interest in methodsfor extracting knowledge from such data is increasing. Through digitalrepresentations of manufacturing operations, future scenarios can be modeledand developed with analysis tools based on simulation in combination withmulti-objective optimisation. The results from such analysis tools may bechallenging to interpret, especially when expanding the scope to searchingfor information patterns. An emerging multi-objective rule extraction method,with the ability to handle discrete input parameters, has been furtherdeveloped towards integration in an intelligent decision support system.
In a Cyber-physical system, the information flow from the cyber part to the physical part plays a crucial role. This paper presents the work of development and initial testing of an augmented reality approach to provide a user interface for operators that could be a part of a robotic production system. The solution is distributed and includes a communication hub that allows the exchange of data and information between multiple clients e.g. robot controllers, an optimization platform, and visualization devices. The main contributions of the presented work are visualization of optimization results and visualization of information obtained from the robot controller and the integrated communication framework. The paper also presents challenges faced during the development work and opportunities related to the presented approach. The implemented interface uses HoloLens 2 mixed reality device to visualize in real-time information obtained from a robot controller as well as from simulation. Information regarding the placement of work objects and targets or currently executed lines of code can be useful for robotic cell programmers and commissioning teams to validate robot programs and to select more optimal solutions toward sustainable manufacturing. The operator can simulate the execution of the robot program and visualize it by overlying the robot cell with the 3D model of the simulated robot. Moreover, visualization of future robot motion could support human-robot collaboration. Furthermore, the interface allows providing the user with details from multi-objective optimization performed on a digital twin of the robotic cell with the aim to reduce cycle time and energy consumption. It allows visualizing selected scenarios to support decision-making by allowing comparison of proposed solutions and the initial one. The visualization includes cell layout, robot path, cycle time, robot energy consumption. The presented approach is demonstrated in industry-inspired cases and with the use of an industrial ABB robot.
The Swedish Postal Services receives and distributes over 22 million pieces of mail every day. Mail transportation takes place overnight by airplanes, trains, trucks, and cars in a transportation network comprising a huge number of possible routes. For testing and analysis of different transport solutions, a discrete-event simulation model of the transportation network has been developed. This paper describes the optimization of transport solutions using evolutionary algorithms coupled with the simulation model. The vast transportation network in combination with a large number of possible transportation configurations and conflicting optimization criteria make the optimization problem very challenging. A large number of simulation evaluations are needed before an acceptable solution is found, making the computational cost of the problem severe. To address this problem, a computationally cheap surrogate model is used to offload the optimization process.
This paper presents a web-based simulation-optimization system for improving production schedules in an advanced manufacturing cell at Volvo Aero Corporation in Sweden. The optimization aims at prioritizing components being processed in the cell in a way that minimizes both tardiness and lead times. Results from evaluating the implemented system shows a great improvement potential, but also indicates that further development is necessary before the system can be taken into operation.
This study presents a platform for industrial, real-world simulation-optimization based on web techniques. The design of the platform is intended to be generic and thereby make it possible to apply the platform in various problem domains. In the implementation of the platform, modern web techniques, such as Ajax, JavaScript, GWT, and ProtoBuf, are used. The platform is tested and evaluated on a real industrial problem of production optimization at Volvo Aero Corporation, a company that develops and manufactures high-technology components for aircraft and gas turbine engines. The results of the evaluation show that while the platform has several benefits, implementing a web-based system is not completely straightforward. At the end of the paper, possible pitfalls are discussed and some recommendations for future implementations are outlined.